1#!/usr/bin/python3 2 3# Copyright 2020 Google LLC 4# 5# Licensed under the Apache License, Version 2.0 (the "License"); 6# you may not use this file except in compliance with the License. 7# You may obtain a copy of the License at 8# 9# http://www.apache.org/licenses/LICENSE-2.0 10# 11# Unless required by applicable law or agreed to in writing, software 12# distributed under the License is distributed on an "AS IS" BASIS, 13# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 14# See the License for the specific language governing permissions and 15# limitations under the License. 16 17import logging 18import sys 19import warnings 20import atheris 21 22from bs4 import BeautifulSoup 23 24 25try: 26 import HTMLParser 27 HTMLParseError = HTMLParser.HTMLParseError 28except ImportError: 29 # HTMLParseError is removed in Python 3.5. Since it can never be 30 # thrown in 3.5, we can just define our own class as a placeholder. 31 32 class HTMLParseError(Exception): 33 pass 34 35 36def TestOneInput(data): 37 """TestOneInput gets random data from the fuzzer, and throws it at bs4.""" 38 if len(data) < 1: 39 return 40 41 parsers = ['lxml-xml', 'html5lib', 'html.parser', 'lxml'] 42 try: 43 idx = int(data[0]) % len(parsers) 44 except ValueError: 45 return 46 47 try: 48 soup = BeautifulSoup(data[1:], features=parsers[idx]) 49 except HTMLParseError: 50 return 51 except ValueError: 52 return 53 54 list(soup.find_all(True)) 55 soup.prettify() 56 57 58def main(): 59 logging.disable(logging.CRITICAL) 60 warnings.filterwarnings('ignore') 61 atheris.Setup(sys.argv, TestOneInput, enable_python_coverage=True) 62 atheris.Fuzz() 63 64 65if __name__ == "__main__": 66 main() 67